CalvinBackup/OBLITERATUS
1
0
Fork 0
mirror of https://github.com/elder-plinius/OBLITERATUS.git synced 2026-08-29 22:20:36 +02:00
Code Issues Packages Projects Releases Wiki Activity

docs: clarify shared-host admission budget

Browse Source
This commit is contained in:
Joseph Magly
2026-08-28 10:46:24 -04:00
parent 683b39ba53
commit 089c6eb5c0
1 changed files with 5 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/deployment/shared-gpu-host.md
+5 -2
View File
@@ -95,7 +95,10 @@ new admission.
Readiness occurs after model allocation, never at UI startup. Set
`OBLITERATUS_GPU_HEARTBEAT_SECONDS` to change the default 15-second heartbeat,
and `OBLITERATUS_GPU_ADMISSION_TIMEOUT_SECONDS` to change the default 30-second
fail-closed acknowledgment timeout.
fail-closed acknowledgment timeout. Shared hosts that must drain another model
server should use a larger measured deadline (120 seconds in the example below)
and require the supervisor's broker timeout plus heartbeat handshake to finish
several seconds before it.
A minimal systemd setup lets the supervisor create the local boundary without
giving the application scheduling authority:
@@ -108,7 +111,7 @@ RuntimeDirectory=obliteratus-gpu-lifecycle
RuntimeDirectoryMode=0770
Environment=OBLITERATUS_GPU_LIFECYCLE_DIR=/run/obliteratus-gpu-lifecycle
Environment=OBLITERATUS_GPU_HEARTBEAT_SECONDS=15
Environment=OBLITERATUS_GPU_ADMISSION_TIMEOUT_SECONDS=30
Environment=OBLITERATUS_GPU_ADMISSION_TIMEOUT_SECONDS=120
ExecStart=/srv/obliteratus/current/.venv/bin/obliteratus ui --host 127.0.0.1
```